تقرير
TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers
| العنوان: | TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers |
|---|---|
| المؤلفون: | Moosmann, Julian, Giordano, Marco, Vogt, Christian, Magno, Michele |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Hardware Architecture, Electrical Engineering and Systems Science - Image and Video Processing |
| الوصف: | This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5MB memory available for storing convolutional neural network (CNN) weights. The proposed quantized network architecture with 422k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators. In particular, the proposed network has been deployed on the MAX78000 microcontroller achieving high frame-rate of up to 180fps and an ultra-low energy consumption of only 196{\mu}J per inference with an inference efficiency of more than 106 MAC/Cycle. TinyissimoYOLO can be trained for any multi-object detection. However, considering the small network size, adding object detection classes will increase the size and memory consumption of the network, thus object detection with up to 3 classes is demonstrated. Furthermore, the network is trained using quantization-aware training and deployed with 8-bit quantization on different microcontrollers, such as STM32H7A3, STM32L4R9, Apollo4b and on the MAX78000's CNN accelerator. Performance evaluations are presented in this paper. Comment: Published In: 2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS) |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1109/AICAS57966.2023.10168657 |
| URL الوصول: | http://arxiv.org/abs/2306.00001 |
| رقم الأكسشن: | edsarx.2306.00001 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1109/AICAS57966.2023.10168657 |
|---|